© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-270M-IT
    3. 12-GEMMASCOPE-2-RES-65K
    4. 2495
    Prev
    Next
    INDEX
    Explanations

    young after comma

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lược
    2.28
    idated
    2.25
     with
    2.21
    ploidy
    2.13
    ’
    2.10
    אה
    2.05
     of
    2.04
    '
    2.02
    おお
    2.00
     to
    1.99
    POSITIVE LOGITS
     compensate
    3.59
     create
    3.42
    kyo
    3.42
     acquire
    3.39
     attenuate
    3.28
     dissipate
    3.27
     deactivate
    3.26
     emit
    3.26
     classify
    3.21
    acquire
    3.19
    Activations Density 0.425%

    No Known Activations